Bayesian bi-clustering methods with applications in computational biology

Bi-clustering is a useful approach in analyzing large biological data sets when the observations come from heterogeneous groups and have number of features. We outline general Bayesian tackling bi-clustering problems moderate to high dimensions propose three models on categorical which increase complexities their modeling distributions features across bi-clusters. Our proposed methods apply wide range scenarios: situations where are cluster-distinguishable only among small subset but masked by amount noise different identified or exhibit hierarchical structures. Through simulation studies we show that our outperform existing (bi-)clustering both identifying clusters recovering feature distributional patterns further developed approaches human genetic dataset, single-cell genomic collection 1774 mouse datasets with focus 58 genes two pathways.